OpenAutoNLU: Open Source AutoML Library for NLU
This provides a practical tool for developers and researchers in natural language processing to streamline NLU workflows, though it is incremental as it builds on existing AutoML concepts.
The authors tackled the problem of automating NLU tasks by developing OpenAutoNLU, an open-source AutoML library that eliminates manual configuration through data-aware training regime selection, achieving a user-friendly lowcode API with integrated features like data quality diagnostics and OOD detection.
OpenAutoNLU is an open-source automated machine learning library for natural language understanding (NLU) tasks, covering both text classification and named entity recognition (NER). Unlike existing solutions, we introduce data-aware training regime selection that requires no manual configuration from the user. The library also provides integrated data quality diagnostics, configurable out-of-distribution (OOD) detection, and large language model (LLM) features, all within a minimal lowcode API. The demo app is accessible here https://openautonlu.dev.